The present invention is directed to a method for generating a library of antigen binding molecules for screening for binding to an epitope of interest, said method comprising: a. selecting a template antigen-binding molecule from a set of possible template antigen binding molecules wherein said selected template does not specifically bind the epitope of interest but is known to specifically bind another epitope; b. selecting at least one residue position in said template antigen-binding molecule for mutation; and c. selecting at least one variant residue to substitute at the at least one residue position selected in b; such that a library containing a plurality of variants of said template is generated.

A method for calculating usage of all alternative polyadenylation sites (PAS) in a genomic sequence includes receiving plural genomic sub-sequences centered on corresponding PAS; processing each genomic sub-sequence of the plural genomic sequences, with a corresponding neural network of plural neural networks; supplying plural outputs of the plural neural networks to an interaction layer that includes plural forward Bidirectional Long Short Term Memory Network (Bi-LSTM) cells and plural backward Bi-LSTM cells, wherein each pair of a forward Bi-LSTM cell and a backward Bi-LSTM cell uniquely receives a corresponding output, of the plural outputs, from a corresponding neural network; and generating a scalar value for each PAS, based on an output from a corresponding pair of the forward Bi-LSTM cell and the backward Bi-LSTM cell.

A method for calculating usage of all alternative polyadenylation sites (PAS) in a genomic sequence includes receiving plural genomic sub-sequences centered on corresponding PAS; processing each genomic sub-sequence of the plural genomic sequences, with a corresponding neural network of plural neural networks; supplying plural outputs of the plural neural networks to an interaction layer that includes plural forward Bidirectional Long Short Term Memory Network (Bi-LSTM) cells and plural backward Bi-LSTM cells, wherein each pair of a forward Bi-LSTM cell and a backward Bi-LSTM cell uniquely receives a corresponding output, of the plural outputs, from a corresponding neural network; and generating a scalar value for each PAS, based on an output from a corresponding pair of the forward Bi-LSTM cell and the backward Bi-LSTM cell.

The present application mainly relates to specific methods for inferring activity of one or more cellular signaling pathway(s) in tissue of a medical subject based at least on the expression level(s) of one or more target gene(s) of the cellular signaling pathway(s) measured in an extracted sample of the tissue of the medical subject, an apparatus comprising a digital compressor configured to perform such methods and a non-transitory storage medium storing instructions that are executable by a digital processing device to perform such methods.

The present application mainly relates to specific methods for inferring activity of one or more cellular signaling pathway(s) in tissue of a medical subject based at least on the expression level(s) of one or more target gene(s) of the cellular signaling pathway(s) measured in an extracted sample of the tissue of the medical subject, an apparatus comprising a digital compressor configured to perform such methods and a non-transitory storage medium storing instructions that are executable by a digital processing device to perform such methods.

The invention provides a method, apparatus, device and storage medium for predicting a protein binding site. The method comprises the steps of: receiving a protein sequence to be predicted, dividing the protein sequence by using a preset sliding window and sliding step to obtain a plurality of amino acid sub-sequences, building word vectors for the protein sequence according to the amino acid sub-sequences, extracting document features from word elements, building document feature vectors for the protein sequence according to the extracted document features, extracting protein chain biological features from the amino acid sub-sequences, building biological feature vectors for the protein sequence according to the extracted biological features, classifying the amino acid sub-sequences expressed with the document feature vectors and the biological feature vectors by using a preset amino acid residue classification model to obtain amino acid residue types for the protein sequence.

The invention provides a method, apparatus, device and storage medium for predicting a protein binding site. The method comprises the steps of: receiving a protein sequence to be predicted, dividing the protein sequence by using a preset sliding window and sliding step to obtain a plurality of amino acid sub-sequences, building word vectors for the protein sequence according to the amino acid sub-sequences, extracting document features from word elements, building document feature vectors for the protein sequence according to the extracted document features, extracting protein chain biological features from the amino acid sub-sequences, building biological feature vectors for the protein sequence according to the extracted biological features, classifying the amino acid sub-sequences expressed with the document feature vectors and the biological feature vectors by using a preset amino acid residue classification model to obtain amino acid residue types for the protein sequence.

Methods and systems for training a model include encoding training peptide sequences using an encoder model. A new peptide sequence is generated using a generator model. The encoder model, the generator model, and the discriminator model are trained to cause the generator model to generate new peptides that the discriminator mistakes for the training peptide sequences, including learning projection vectors with respective cross-entropy losses for binding sequences and non-binding sequences.

Methods and systems for training a model include encoding training peptide sequences using an encoder model. A new peptide sequence is generated using a generator model. The encoder model, the generator model, and the discriminator model are trained to cause the generator model to generate new peptides that the discriminator mistakes for the training peptide sequences, including learning projection vectors with respective cross-entropy losses for binding sequences and non-binding sequences.

This disclosure relates generally to method and system for structure-based drug design using a multi-modal deep learning model. The method processes a target protein for designing at least one optimized molecule by using a multi-modal deep learning model. The GAT-VAE module obtains a latent vector of at least one active site graph comprising of key amino acid residues from the target protein. The SMILES-VAE module obtains at least one latent vector from the target protein. Further, the conditional molecular generator concatenates the active site graph with the latent vector to generate a set of molecules. The RL framework is iteratively performed on the concatenated latent vector to optimize at least one molecule by using the drug-target affinity (DTA) predictor module to predict an affinity value for the set of molecules towards the target protein. Further, at least one optimized molecule is designed with an affinity of the target protein.